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

    Neuronpedia

    INDEX
    Explanations

    terms related to unlocking and evaluating worth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    penup
    -0.48
    ngdoc
    -0.48
    blanc
    -0.47
    idän
    -0.46
    巴掌
    -0.46
    ursor
    -0.45
    Externe
    -0.44
    झे
    -0.44
    toPromise
    -0.44
     bother
    -0.44
    POSITIVE LOGITS
     Bea
    1.20
    Bea
    1.09
    bea
    0.99
     bea
    0.96
     unlocked
    0.75
     unlock
    0.74
    streams
    0.73
    __":
    0.71
     streams
    0.70
     BEA
    0.69
    Act Density 0.099%

    No Known Activations