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

    Neuronpedia

    INDEX
    Explanations

    opening statements or summaries at the beginning of sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.83
    osexuality
    -0.70
    -0.69
     arşivlendi
    -0.69
    Geografi
    -0.67
    HostException
    -0.65
     Efq
    -0.65
    istoitu
    -0.64
     imidlertid
    -0.64
    elemField
    -0.64
    POSITIVE LOGITS
            
    0.60
    стероид
    0.59
     يتيمه
    0.57
    0.54
    <bos>
    0.53
     referenties
    0.53
    3
    0.52
    ressen
    0.47
    ereço
    0.46
    daily
    0.45
    Act Density 0.308%

    No Known Activations