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

    Neuronpedia

    INDEX
    Explanations

    mentions of promises or commitments to take a specific action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pledged"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ther
    -0.84
    pmwiki
    -0.81
     Modified
    -0.66
    dos
    -0.66
    psy
    -0.65
    Else
    -0.65
    opus
    -0.64
    Phoenix
    -0.64
    occ
    -0.64
     Ain
    -0.63
    POSITIVE LOGITS
     pledges
    1.01
     allegiance
    0.97
     pledging
    0.92
     pledged
    0.89
     commitments
    0.80
     pledge
    0.79
     encour
    0.78
    itivity
    0.76
    irection
    0.73
     commitment
    0.73
    Act Density 0.012%

    No Known Activations