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

    Neuronpedia

    INDEX
    Explanations

    conditional terms related to propositions or clauses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditionality and unconditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arks
    -0.80
    azines
    -0.77
    geist
    -0.76
    ulz
    -0.75
     Illustrated
    -0.74
    sonian
    -0.73
    hoff
    -0.72
    Desk
    -0.72
     Dull
    -0.71
     Metall
    -0.71
    POSITIVE LOGITS
     uncond
    1.24
     unconditional
    1.20
     confir
    1.07
     conditional
    1.00
    etheless
    0.94
     surrender
    0.92
    itionally
    0.91
     conditioned
    0.90
     subord
    0.86
     pacif
    0.85
    Act Density 0.015%

    No Known Activations