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

    Neuronpedia

    INDEX
    Explanations

    connectors or conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpeg
    -0.90
    ige
    -0.86
    actionDate
    -0.81
    activity
    -0.80
    AU
    -0.77
    SPA
    -0.75
    quad
    -0.70
    panel
    -0.69
    vec
    -0.69
    ema
    -0.69
    POSITIVE LOGITS
    romeda
    0.93
     secondly
    0.79
    rew
    0.77
    rogen
    0.76
     optionally
    0.74
     furthermore
    0.73
     Kushner
    0.69
     maybe
    0.68
     vo
    0.68
     vice
    0.68
    Act Density 0.080%

    No Known Activations