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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizations and systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Copyright
    -0.57
    cigarettes
    -0.51
    LOS
    -0.51
    continental
    -0.50
    Enlarge
    -0.50
    ':
    -0.50
    wcsstore
    -0.49
    pron
    -0.49
    Untitled
    -0.49
    Born
    -0.48
    POSITIVE LOGITS
     however
    1.05
     moreover
    0.90
     therefore
    0.90
     meanwhile
    0.86
     furthermore
    0.83
    anwhile
    0.71
     also
    0.68
     though
    0.66
     additionally
    0.63
     thus
    0.63
    Act Density 2.529%

    No Known Activations