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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.65
    soDeliveryDate
    -0.49
     assorted
    -0.49
     doubtless
    -0.49
    atari
    -0.48
    auri
    -0.48
    accompanied
    -0.47
     hopefully
    -0.47
    ortment
    -0.46
    adder
    -0.45
    POSITIVE LOGITS
     anymore
    1.80
     nor
    1.58
     whatsoever
    1.23
     anywhere
    1.06
     anything
    1.02
     slightest
    1.00
    yet
    1.00
     any
    0.97
     anybody
    0.93
     yet
    0.89
    Act Density 1.674%

    No Known Activations