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

    Neuronpedia

    INDEX
    Explanations

    mentions of residents and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ù
    -0.19
    oes
    -0.18
    oul
    -0.17
     Morr
    -0.15
    ologies
    -0.15
    resse
    -0.15
    lopen
    -0.15
    ww
    -0.15
    ź
    -0.14
    μÎŃ
    -0.14
    POSITIVE LOGITS
    ials
    0.23
    ally
    0.20
    evil
    0.20
    RIC
    0.18
    rics
    0.17
    ric
    0.17
     Evil
    0.17
    iles
    0.16
    ILES
    0.16
     halls
    0.15
    Act Density 0.022%

    No Known Activations