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

    Neuronpedia

    INDEX
    Explanations

    phrases describing a person or team's recent performance or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate recovery or return from a previous state or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.79
    %]
    -0.74
    amount
    -0.71
    ilation
    -0.70
    RL
    -0.68
    ãĤ±
    -0.68
    OTT
    -0.66
    MX
    -0.66
    KS
    -0.65
    jad
    -0.64
    POSITIVE LOGITS
    site
    0.75
    ibaba
    0.73
    loaded
    0.71
    screen
    0.71
     pist
    0.69
     leash
    0.68
     Broadway
    0.67
    stage
    0.66
    loading
    0.66
     fumes
    0.64
    Act Density 0.022%

    No Known Activations