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

    Neuronpedia

    INDEX
    Explanations

    instances of being compelled or coerced into actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ven
    -0.16
    ji
    -0.15
    dt
    -0.15
    ssel
    -0.15
    Ãľ
    -0.14
     reward
    -0.14
    анÑģи
    -0.14
    ploy
    -0.14
    reo
    -0.14
    ãģŁãĤī
    -0.14
    POSITIVE LOGITS
     into
    0.29
     onto
    0.25
    into
    0.24
    Into
    0.18
     Into
    0.18
     upon
    0.18
     Forced
    0.18
    -feed
    0.18
    onto
    0.18
    forced
    0.18
    Act Density 0.033%

    No Known Activations