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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events in progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocard
    -0.69
    raped
    -0.68
    rug
    -0.67
    umbo
    -0.67
    bel
    -0.66
    verbs
    -0.66
    phone
    -0.66
     Parables
    -0.65
    pi
    -0.65
    cig
    -0.64
    POSITIVE LOGITS
     underway
    0.97
     anew
    0.75
    CLASSIFIED
    0.74
    spection
    0.73
    ESSION
    0.71
     tonight
    0.71
    FIELD
    0.67
    rontal
    0.67
     Phase
    0.67
     proceedings
    0.66
    Act Density 0.032%

    No Known Activations