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

    Neuronpedia

    INDEX
    Explanations

    the word "vert" or variations of it such as "vertex" or "avert" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    words related to subversion or undermining authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.82
    çĦ
    -0.76
    utical
    -0.75
    Interstitial
    -0.70
    senal
    -0.69
    ptive
    -0.68
     Bei
    -0.65
    ptives
    -0.65
    Aw
    -0.62
    andro
    -0.61
    POSITIVE LOGITS
    ibility
    1.01
    verted
    0.99
    version
    0.91
    ophobia
    0.83
    ibly
    0.81
    verts
    0.80
    ible
    0.79
    ibilities
    0.76
    verting
    0.76
    ected
    0.74
    Act Density 0.031%

    No Known Activations