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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and expressing clarity in communication

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

    Preceding "that"

    np_acts-logits-general · gemini-2.0-flash

    than that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.60
    [++
    -0.51
     här
    -0.48
    )|^{
    -0.47
    here
    -0.47
    際
    -0.42
    nach
    -0.42
     ici
    -0.41
     _,
    -0.41
     Ici
    -0.41
    POSITIVE LOGITS
     That
    2.01
    That
    1.93
    那個
    1.85
     that
    1.84
     those
    1.82
     THAT
    1.81
    那个
    1.81
     thats
    1.71
    THAT
    1.69
     ese
    1.64
    Act Density 1.303%

    No Known Activations