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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events being carried out

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĥ
    -0.68
    Imagine
    -0.64
    ãĥ¯
    -0.62
     Suddenly
    -0.61
    amins
    -0.61
    bec
    -0.61
     nep
    -0.60
    riter
    -0.60
     Izan
    -0.58
    Suddenly
    -0.58
    POSITIVE LOGITS
     unsuccessful
    0.74
     satisfactory
    0.73
     unsuccessfully
    0.70
     successful
    0.68
     indications
    0.67
    successful
    0.66
     sparing
    0.66
     only
    0.65
    TERN
    0.64
     satisf
    0.63
    Act Density 0.083%

    No Known Activations