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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings or negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    elements related to quantity or numerical values associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥ŀ
    -0.64
    obo
    -0.60
    Fat
    -0.60
    agon
    -0.58
    Port
    -0.58
    uder
    -0.58
    Ton
    -0.57
    Mor
    -0.56
    OB
    -0.56
    mitter
    -0.55
    POSITIVE LOGITS
     and
    0.98
    and
    0.98
     AND
    0.87
    &
    0.78
     &
    0.76
    andi
    0.74
    andan
    0.72
    soType
    0.72
     partName
    0.70
    ands
    0.67
    Act Density 0.156%

    No Known Activations