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

    Neuronpedia

    INDEX
    Explanations

    expressions related to joining or participating in activities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.15
    agna
    -0.15
    enga
    -0.15
    zza
    -0.15
    uda
    -0.15
    /of
    -0.15
    ToLower
    -0.15
    bye
    -0.14
    çĦ¶
    -0.14
    ynch
    -0.14
    POSITIVE LOGITS
     forces
    0.60
    forces
    0.47
     Forces
    0.43
     ranks
    0.38
     force
    0.36
     hands
    0.33
     forced
    0.27
    force
    0.27
    forced
    0.25
     efforts
    0.25
    Act Density 0.027%

    No Known Activations