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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "scan" or related variations in the context of research or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pengu
    -0.67
     Kut
    -0.64
     manslaughter
    -0.63
     Yog
    -0.59
     Cind
    -0.59
     laure
    -0.58
     ment
    -0.58
    Aid
    -0.57
     rapp
    -0.56
     Masquerade
    -0.56
    POSITIVE LOGITS
    lator
    1.19
    lations
    1.08
    ning
    1.05
    nery
    0.96
    lan
    0.94
    lon
    0.93
    lation
    0.91
     scans
    0.89
    ner
    0.87
     scan
    0.87
    Act Density 0.062%

    No Known Activations