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

    Neuronpedia

    INDEX
    Explanations

    references to beginning, starting, or entering various stages or phases of something

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to entering or joining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hoax
    -0.75
     Mong
    -0.68
    killer
    -0.67
    cop
    -0.67
    oho
    -0.67
     ®
    -0.66
    tein
    -0.65
    apo
    -0.62
    ombat
    -0.59
    bell
    -0.59
    POSITIVE LOGITS
     halftime
    0.77
    isSpecialOrderable
    0.76
    Constructed
    0.70
    ournament
    0.69
    ardless
    0.68
     stride
    0.68
    flush
    0.67
     Flames
    0.66
     preseason
    0.66
    former
    0.66
    Act Density 0.036%

    No Known Activations