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

    Neuronpedia

    INDEX
    Explanations

    verbs describing actions or decisions influenced by choices, such as 'waiting', 'relying', 'trying', 'silence', 'confronting', and 'recognizing'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating alternative actions or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rongh
    -0.68
    quad
    -0.68
    bon
    -0.66
    marked
    -0.64
    added
    -0.64
     Adin
    -0.63
    perty
    -0.63
    mma
    -0.63
     Âł Âł Âł Âł
    -0.62
    rolet
    -0.62
    POSITIVE LOGITS
     blindly
    0.81
     altogether
    0.77
     excuses
    0.76
     anymore
    0.75
     outright
    0.74
    udicrous
    0.74
     passively
    0.71
     anything
    0.69
     simplistic
    0.67
     inconvenient
    0.65
    Act Density 0.159%

    No Known Activations