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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe potential risks or dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arend
    -0.16
     NÄĽkter
    -0.15
     Shared
    -0.15
    ietet
    -0.14
     Canter
    -0.14
    rif
    -0.14
    TEGER
    -0.14
     Podle
    -0.13
    atif
    -0.13
    _vlog
    -0.13
    POSITIVE LOGITS
     combination
    0.69
     combined
    0.59
     combine
    0.59
    combination
    0.56
     combo
    0.55
    combined
    0.54
     Combination
    0.53
     Combine
    0.52
     combinations
    0.52
    Combine
    0.50
    Act Density 0.462%

    No Known Activations