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

    Neuronpedia

    INDEX
    Explanations

    terms indicating evaluation or judgment of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atility
    -0.55
     reconn
    -0.53
     asked
    -0.53
     recognized
    -0.52
     diketahui
    -0.52
    findpost
    -0.51
     stated
    -0.51
     recognised
    -0.51
     acknowledged
    -0.49
     complained
    -0.49
    POSITIVE LOGITS
     worthy
    0.93
     unworthy
    0.82
     unsuitable
    0.78
     suitable
    0.76
    worthy
    0.74
     unfit
    0.73
     belonging
    0.73
     acceptable
    0.72
    suitable
    0.72
     worthwhile
    0.72
    Act Density 0.717%

    No Known Activations