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

    Neuronpedia

    INDEX
    Explanations

    references to providing access to a collection or source of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate access to information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REF
    -0.72
    teenth
    -0.72
    irtual
    -0.66
     eater
    -0.65
    caster
    -0.65
    break
    -0.65
    psc
    -0.65
    MSN
    -0.64
    Downloadha
    -0.63
    model
    -0.63
    POSITIVE LOGITS
    ©¶æ
    0.75
     Kissinger
    0.68
     rejo
    0.66
     thanking
    0.65
    utsche
    0.65
     Cue
    0.65
     Broadcasting
    0.61
    plex
    0.60
    Rog
    0.59
     Bohem
    0.58
    Act Density 0.000%

    No Known Activations