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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to providing services or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.87
    FACE
    -0.68
    masters
    -0.67
    worthy
    -0.65
    DAY
    -0.65
    grass
    -0.65
     Monarch
    -0.63
     Goo
    -0.63
    SEE
    -0.62
    san
    -0.61
    POSITIVE LOGITS
    incial
    1.13
    prov
    0.96
    osed
    0.94
    assion
    0.93
    ince
    0.91
    idence
    0.90
    ided
    0.88
    iders
    0.88
    atoon
    0.87
    achu
    0.86
    Act Density 0.019%

    No Known Activations