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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or permission

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and expressions of possibility or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.66
    hig
    -0.63
    advertisement
    -0.63
     Simulator
    -0.59
     Dragonbound
    -0.58
    Dial
    -0.55
     Position
    -0.54
     [-
    -0.54
     Working
    -0.53
    esa
    -0.52
    POSITIVE LOGITS
     they
    1.30
     we
    1.19
     you
    1.13
     it
    1.10
     he
    1.07
     THEY
    0.97
     anybody
    0.95
     she
    0.95
     ya
    0.95
     there
    0.94
    Act Density 0.128%

    No Known Activations