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

    Neuronpedia

    INDEX
    Explanations

    references to code functionality and methods related to data structures and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الحياه
    -0.72
    expandindo
    -0.71
    adaptiveStyles
    -0.68
    igshid
    -0.63
     our
    -0.58
    __':
    -0.56
     Somewhere
    -0.55
     somehow
    -0.55
     Somehow
    -0.53
    ViewFeatures
    -0.53
    POSITIVE LOGITS
     defaults
    0.88
     Defaults
    0.81
    Defaults
    0.78
    defaults
    0.77
    默认为
    0.69
     Infórmanos
    0.69
     defaulted
    0.68
     Deprecated
    0.67
     default
    0.66
     optionally
    0.63
    Act Density 0.786%

    No Known Activations