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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement and disagreement in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rol
    -0.17
    bol
    -0.15
    rop
    -0.15
    лÑİб
    -0.15
     McCabe
    -0.15
    yy
    -0.14
    ounter
    -0.14
    sole
    -0.14
    åĪ¶
    -0.14
    tel
    -0.14
    POSITIVE LOGITS
     agree
    0.22
     completely
    0.21
     totally
    0.21
    agree
    0.21
     assessment
    0.20
     sentiments
    0.19
     sentiment
    0.19
     whole
    0.18
     Totally
    0.18
     entirely
    0.18
    Act Density 0.041%

    No Known Activations