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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "attitude" and its variations, indicating perspectives or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĮĢ
    -0.18
    oria
    -0.15
    emann
    -0.15
    olan
    -0.14
    _CONV
    -0.14
    rej
    -0.14
    cela
    -0.14
    iginal
    -0.14
    chwitz
    -0.14
    olars
    -0.14
    POSITIVE LOGITS
     toward
    0.25
     towards
    0.24
     attitude
    0.20
     Towards
    0.19
     attitudes
    0.19
    istically
    0.19
    ally
    0.18
     wonder
    0.17
     Tow
    0.17
     disposition
    0.17
    Act Density 0.017%

    No Known Activations