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

    Neuronpedia

    INDEX
    Explanations

    words related to legal language or terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exemptions and comparisons across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thanking
    -0.70
     flanked
    -0.62
     thanked
    -0.59
    amo
    -0.54
     --------------------------------
    -0.54
    CHAT
    -0.54
     promptly
    -0.54
     ``
    -0.53
    ↵Âł
    -0.53
     preferably
    -0.52
    POSITIVE LOGITS
     counterparts
    0.81
     predecessors
    0.70
     nor
    0.69
     equivalents
    0.69
     ones
    0.67
     anymore
    0.64
     predec
    0.62
     attRot
    0.62
     altogether
    0.61
     peers
    0.60
    Act Density 0.798%

    No Known Activations