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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solve
    -0.20
    eyim
    -0.14
    Trait
    -0.13
    istrovstvÃŃ
    -0.13
    ooth
    -0.12
    .observe
    -0.12
    auce
    -0.12
    оÑģÑĤи
    -0.12
    ÑĪев
    -0.12
    ught
    -0.12
    POSITIVE LOGITS
     type
    1.08
     kind
    1.08
     kinds
    1.02
     types
    0.92
    kind
    0.84
    type
    0.82
     sort
    0.80
     sorts
    0.78
     tipo
    0.77
    -type
    0.74
    Act Density 0.463%

    No Known Activations