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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term considerations or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to long-term and short-term outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othing
    -0.73
    yne
    -0.71
    MSN
    -0.68
     Bleach
    -0.68
    ymes
    -0.67
     Flavoring
    -0.64
    ofer
    -0.64
    utenberg
    -0.64
    zo
    -0.63
    atche
    -0.63
    POSITIVE LOGITS
     term
    0.98
    term
    0.97
     aftermath
    0.94
     absence
    0.90
     afterlife
    0.89
     confines
    0.88
     timeframe
    0.83
     haul
    0.80
     vicinity
    0.79
     run
    0.79
    Act Density 0.058%

    No Known Activations