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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .sap
    -0.16
     throughout
    -0.15
    entine
    -0.15
    áÅĻe
    -0.14
    kins
    -0.14
    Ùħت
    -0.14
    çĻ
    -0.14
    ertime
    -0.14
    jin
    -0.13
    /we
    -0.13
    POSITIVE LOGITS
     which
    0.19
    which
    0.17
    /of
    0.16
    ora
    0.16
     οÏĢοίο
    0.16
     someone
    0.16
     коÑĤоÑĢÑĭй
    0.15
    ottage
    0.15
     somebody
    0.15
     called
    0.14
    Act Density 0.505%

    No Known Activations