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

    Neuronpedia

    INDEX
    Explanations

    repeated expressions of surprise or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.76
    "])
    -0.65
    PyErr
    -0.63
    XmlAccessType
    -0.62
    ']))
    -0.60
    .}}
    -0.58
    "]];
    -0.58
    "]}
    -0.56
    ."],
    -0.56
     Ever
    -0.55
    POSITIVE LOGITS
     mothers
    0.85
     caufe
    0.74
    Aholisi
    0.73
     protoimpl
    0.71
     chofe
    0.69
     pleaſure
    0.67
     ſur
    0.67
     fathers
    0.67
     ſame
    0.66
     reaſon
    0.66
    Act Density 0.137%

    No Known Activations