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

    Neuronpedia

    INDEX
    Explanations

    research-related concepts and actions that involve investigation, assessment, and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.77
    <bos>
    -0.69
    2
    -0.55
    this
    -0.54
    1
    -0.54
     this
    -0.52
     ibunya
    -0.52
     másik
    -0.51
    '
    -0.51
    这个
    -0.51
    POSITIVE LOGITS
    ^(@
    1.20
    Portale
    1.16
    olesale
    1.09
    ^(@)
    1.09
     snippetHide
    1.04
     CURIAM
    0.99
    ſelves
    0.97
     ―――――
    0.97
     $_"
    0.95
     various
    0.93
    Act Density 1.276%

    No Known Activations