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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and terms related to political discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaru
    -0.67
    tom
    -0.63
    vertisements
    -0.61
    nova
    -0.60
    ezvous
    -0.60
    Thumbnail
    -0.60
    venants
    -0.59
    oshenko
    -0.58
    nown
    -0.58
    ril
    -0.58
    POSITIVE LOGITS
     sake
    1.36
     purposes
    1.25
     reasons
    1.05
     reason
    0.70
    erning
    0.69
    icion
    0.69
     lovers
    0.67
     alike
    0.65
     aspiring
    0.64
    ummies
    0.63
    Act Density 0.194%

    No Known Activations