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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases related to decision-making and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istle
    -0.16
     possession
    -0.15
    ancel
    -0.14
     QSize
    -0.14
     reason
    -0.14
    olic
    -0.14
    PerPixel
    -0.14
    OLLOW
    -0.14
    321
    -0.13
    ensch
    -0.13
    POSITIVE LOGITS
     located
    0.20
    located
    0.20
    -hide
    0.17
     hiding
    0.17
     Located
    0.17
    Located
    0.16
     hide
    0.16
     locate
    0.16
     headed
    0.16
    sert
    0.15
    Act Density 0.113%

    No Known Activations