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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Tar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elho
    -0.18
    ello
    -0.18
    ToFront
    -0.17
    EXPR
    -0.16
    iaz
    -0.15
    лина
    -0.15
    ारण
    -0.14
    isas
    -0.14
    sert
    -0.14
    ene
    -0.14
    POSITIVE LOGITS
     Tar
    0.19
     tar
    0.18
    aul
    0.18
    Tar
    0.17
     Harbor
    0.17
    ropolis
    0.17
    bÃŃ
    0.16
     Coalition
    0.15
    ainless
    0.15
    iffs
    0.15
    Act Density 0.013%

    No Known Activations