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

    Neuronpedia

    INDEX
    Explanations

    predictions and anticipations related to future events and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    317
    -0.15
    lah
    -0.15
    zac
    -0.15
    oko
    -0.15
    ellt
    -0.15
    840
    -0.14
    istrovstvÃŃ
    -0.14
    uelle
    -0.14
    ä¹ħ
    -0.14
     ends
    -0.13
    POSITIVE LOGITS
     ahead
    0.82
    ahead
    0.74
     Ahead
    0.73
    Ahead
    0.66
    -ahead
    0.54
     впеÑĢед
    0.44
     upcoming
    0.39
     forthcoming
    0.38
     lie
    0.36
     lies
    0.32
    Act Density 0.165%

    No Known Activations