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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making an effort or commitment

    oai_token-act-pair · gpt-3.5-turbo

    actions related to making commitments or expressing intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artney
    -0.70
    pload
    -0.60
     Colleges
    -0.59
    VERTISEMENT
    -0.59
    astical
    -0.55
     Published
    -0.55
     inaccessible
    -0.54
     Motorsport
    -0.53
     Organisation
    -0.52
    BALL
    -0.52
    POSITIVE LOGITS
     myself
    1.45
     my
    0.98
    arest
    0.88
    poke
    0.87
    rely
    0.83
     mine
    0.80
    ELY
    0.77
    raf
    0.74
     yours
    0.73
    REDACTED
    0.72
    Act Density 0.209%

    No Known Activations