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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and human interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    celik
    -0.17
    nh
    -0.16
    spender
    -0.15
    nell
    -0.14
    AFX
    -0.14
    insky
    -0.14
    lements
    -0.14
    velt
    -0.14
    ано
    -0.14
    eneral
    -0.14
    POSITIVE LOGITS
    axter
    0.16
    ailles
    0.16
    orman
    0.15
     Dit
    0.15
     volumes
    0.14
    akit
    0.14
    elyn
    0.14
    олж
    0.13
    ixer
    0.13
     prepared
    0.13
    Act Density 0.974%

    No Known Activations