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

    Neuronpedia

    INDEX
    Explanations

    keywords related to descriptions of objects or entities that are in a state of disrepair

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    overs
    -0.47
    Aren
    -0.46
    AUD
    -0.46
    Events
    -0.46
    sheets
    -0.45
    En
    -0.44
    eworks
    -0.44
    outs
    -0.44
    aways
    -0.44
     besides
    -0.44
    POSITIVE LOGITS
     lot
    0.58
     bunch
    0.56
    venge
    0.55
    usterity
    0.55
    uras
    0.54
    versive
    0.53
    sexual
    0.52
     comma
    0.51
     prostitute
    0.51
     nutshell
    0.51
    Act Density 0.566%

    No Known Activations