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

    Neuronpedia

    INDEX
    Explanations

    words related to influencing or persuading others

    oai_token-act-pair · gpt-3.5-turbo

    words related to influence and persuasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.82
    ICO
    -0.72
    ctica
    -0.71
    arenthood
    -0.66
    isodes
    -0.66
    ospital
    -0.66
    ONE
    -0.66
    ENA
    -0.65
    ãģ®æ
    -0.65
    ãĥ¼ãĥ³
    -0.63
    POSITIVE LOGITS
     sway
    1.39
     pedd
    0.95
     perspect
    0.87
     tremend
    0.82
     swayed
    0.79
    unda
    0.77
    eering
    0.77
    gie
    0.73
    psey
    0.73
    pole
    0.73
    Act Density 0.005%

    No Known Activations