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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or instructions corresponding to turning or rotation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to turns in gameplay or decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.81
    è¦ļéĨĴ
    -0.76
    inately
    -0.76
    llah
    -0.70
    gdala
    -0.66
    anyahu
    -0.65
    foundation
    -0.64
    hammad
    -0.63
    ickson
    -0.63
    capacity
    -0.62
    POSITIVE LOGITS
    buck
    1.00
    about
    0.88
    abouts
    0.84
    around
    0.80
    aho
    0.79
    nings
    0.78
    bum
    0.77
    overs
    0.75
    turn
    0.74
    coat
    0.74
    Act Density 0.030%

    No Known Activations