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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to movement or directional changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahas
    -0.15
    habi
    -0.15
    ål
    -0.14
     bomber
    -0.14
    .yy
    -0.14
    VES
    -0.14
    ahat
    -0.13
    adele
    -0.13
    chop
    -0.13
    487
    -0.13
    POSITIVE LOGITS
    /down
    0.17
    wards
    0.16
     Roth
    0.15
    allocator
    0.14
    osci
    0.14
    NSE
    0.14
    /out
    0.13
    ãĥªãĤ¹
    0.13
    ilos
    0.13
     Frank
    0.13
    Act Density 0.365%

    No Known Activations