Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of customer satisfaction and dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a form of "I am/was/were [feeling/action]"

    np_acts-logits-general · gemini-2.0-flash

    states of being or feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manifestazione
    -0.55
     šķ
    -0.54
    >{@
    -0.52
     femininas
    -0.51
    Desta
    -0.51
     Italijanski
    -0.51
    )|^{
    -0.50
     Италијани
    -0.50
     convocatoria
    -0.50
    DockStyle
    -0.49
    POSITIVE LOGITS
     satisfied
    0.72
     unable
    0.70
     unsure
    0.66
     dissatisfied
    0.65
     using
    0.65
     disappointed
    0.64
     comfortable
    0.64
     impressed
    0.64
    WEBPACK
    0.63
     able
    0.60
    Act Density 0.244%

    No Known Activations