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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hypothetical situations and potential actions

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs expressing conditionality or inevitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reality
    -0.62
     Slayer
    -0.61
    igma
    -0.60
    pires
    -0.60
    ensitive
    -0.60
    ament
    -0.60
     Trap
    -0.59
    ZI
    -0.58
    Tumblr
    -0.58
    ustainable
    -0.57
    POSITIVE LOGITS
     be
    1.06
     arrive
    0.97
     derive
    0.89
     also
    0.88
     become
    0.86
     likewise
    0.85
     incorporate
    0.84
     doubtless
    0.83
     revert
    0.83
     propose
    0.83
    Act Density 0.318%

    No Known Activations