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

    Neuronpedia

    INDEX
    Explanations

    mentions of upcoming or forthcoming events or things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "coming" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.92
    sett
    -0.80
    wart
    -0.79
    nington
    -0.76
    picking
    -0.76
    arg
    -0.75
    vet
    -0.74
    ARS
    -0.74
    acca
    -0.73
    rest
    -0.73
    POSITIVE LOGITS
     attractions
    0.94
    bies
    0.78
     Releases
    0.73
     Showdown
    0.73
     Directions
    0.73
    ãĤĬ
    0.71
     Neigh
    0.71
     FEC
    0.69
     engagements
    0.69
     Ones
    0.68
    Act Density 0.011%

    No Known Activations