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

    Neuronpedia

    INDEX
    Explanations

    phrases that establish rules or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.92
    tvguidetime
    -0.89
     Мексичка
    -0.82
    ViewFeatures
    -0.80
    DockStyle
    -0.78
     AssemblyCulture
    -0.76
    fjspx
    -0.75
    issory
    -0.74
     /\.
    -0.73
    ISupport
    -0.73
    POSITIVE LOGITS
     be
    0.96
     always
    0.59
     not
    0.58
    be
    0.57
     must
    0.55
    Be
    0.54
     helst
    0.53
     have
    0.52
     never
    0.51
     also
    0.51
    Act Density 0.238%

    No Known Activations