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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to reporting and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hasMoreElements
    -0.82
     "..\..\
    -0.73
    ngrx
    -0.70
    vir
    -0.69
     оригіналу
    -0.66
    jsii
    -0.66
     transfieras
    -0.65
    WillAppear
    -0.64
    Aholisi
    -0.62
    ->___
    -0.62
    POSITIVE LOGITS
     uſed
    0.88
     myſelf
    0.78
     itſelf
    0.76
     becauſe
    0.72
     themſelves
    0.69
    moiselle
    0.69
     raiſ
    0.69
    ielded
    0.65
     vinted
    0.63
     poffible
    0.63
    Act Density 0.486%

    No Known Activations