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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future events or actions

    oai_token-act-pair · gpt-3.5-turbo

    future events and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essing
    -0.55
    Exc
    -0.54
    dding
    -0.53
    Zone
    -0.53
    mens
    -0.53
     Guess
    -0.52
    doctor
    -0.52
     Wyatt
    -0.52
    Congratulations
    -0.51
    choice
    -0.51
    POSITIVE LOGITS
     raining
    0.77
     metast
    0.76
     declass
    0.72
     aired
    0.68
     lasted
    0.67
     premiered
    0.67
     contains
    0.65
     landfall
    0.64
    CVE
    0.64
     reprint
    0.64
    Act Density 0.642%

    No Known Activations