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

    Neuronpedia

    INDEX
    Explanations

    phrases related to invitations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of invasive actions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħ¢
    -0.82
    Ĥ¬
    -0.74
     separating
    -0.68
    grass
    -0.67
     horizontally
    -0.66
    ¥µ
    -0.65
    ©¶æ
    -0.64
    dress
    -0.63
     cleaner
    -0.63
     blending
    -0.63
    POSITIVE LOGITS
    itations
    1.33
    itational
    1.32
    incible
    1.31
    igor
    1.29
    ulnerable
    1.19
    asion
    1.17
    itation
    1.17
    oice
    1.16
    idious
    1.14
    asions
    1.13
    Act Density 0.015%

    No Known Activations