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

    Neuronpedia

    INDEX
    Explanations

    themes related to anticipation and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.15
    well
    -0.14
     Closet
    -0.14
    صب
    -0.14
    abor
    -0.14
    ube
    -0.14
    许
    -0.14
    boy
    -0.14
    каÑĢ
    -0.14
    wall
    -0.13
    POSITIVE LOGITS
    ed
    0.29
    ing
    0.27
    /down
    0.22
    edly
    0.22
    .gov
    0.20
    ted
    0.20
    ting
    0.19
    ers
    0.18
    gers
    0.18
    edl
    0.18
    Act Density 0.606%

    No Known Activations