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

    Neuronpedia

    INDEX
    Explanations

    information about a particular publication or program and actions related to supporting it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ensions
    -0.82
    acters
    -0.73
    ön
    -0.70
    heet
    -0.68
    eger
    -0.67
    utic
    -0.66
    cone
    -0.66
    bole
    -0.65
    hops
    -0.65
    omething
    -0.64
    POSITIVE LOGITS
    ally
    0.84
    wide
    0.82
    ukong
    0.81
    arium
    0.80
     Travels
    0.76
    icans
    0.75
     Organization
    0.75
    ican
    0.74
    States
    0.72
    naire
    0.71
    Act Density 4.910%

    No Known Activations