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

    Neuronpedia

    INDEX
    Explanations

    words related to various ideologies or "-isms."

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the suffix "ism" indicating ideological or theoretical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FACE
    -0.76
    STON
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    umm
    -0.64
    ergy
    -0.63
    fman
    -0.62
    VID
    -0.61
    vag
    -0.61
     pad
    -0.61
     Pad
    -0.60
    POSITIVE LOGITS
    yip
    1.25
    atics
    1.22
    ophical
    1.00
    atism
    1.00
    atic
    0.98
    edia
    0.98
    icism
    0.93
    otive
    0.92
    ophobic
    0.90
    atical
    0.89
    Act Density 0.052%

    No Known Activations