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

    Neuronpedia

    INDEX
    Explanations

    expressions of intent or purpose related to goals and aims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uous
    -0.19
    es
    -0.17
    edom
    -0.16
    esa
    -0.15
    an
    -0.15
    astle
    -0.14
    olio
    -0.14
    _pb
    -0.14
    icol
    -0.14
    nee
    -0.14
    POSITIVE LOGITS
    lessly
    0.28
    yro
    0.19
     Aim
    0.19
    /target
    0.17
    aim
    0.17
    erais
    0.16
    tır
    0.16
     aim
    0.16
    ÑĤеÑģÑĮ
    0.16
    /go
    0.15
    Act Density 0.014%

    No Known Activations