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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or activities that could be perceived as bold or daring

    oai_token-act-pair · gpt-3.5-turbo

    themes related to adventures and exploits, particularly involving notable actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shank
    -0.67
    proof
    -0.66
     sleeper
    -0.66
    condition
    -0.65
     psychiatrists
    -0.64
     reinforcement
    -0.63
    ISH
    -0.61
    --+
    -0.60
     accommodation
    -0.60
    hospital
    -0.59
    POSITIVE LOGITS
    cape
    1.24
    ongs
    0.88
    hip
    0.88
    peed
    0.80
    cart
    0.80
     fortunes
    0.79
    linger
    0.78
    uits
    0.77
    chool
    0.76
     revolving
    0.75
    Act Density 0.061%

    No Known Activations