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

    Neuronpedia

    INDEX
    Explanations

    words related to capturing or being captured

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to capturing or documenting experiences or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amily
    -0.65
    ulo
    -0.62
    iop
    -0.62
    jab
    -0.60
    iquette
    -0.59
    reviewed
    -0.59
    prep
    -0.59
    bush
    -0.57
    lease
    -0.57
    wait
    -0.56
    POSITIVE LOGITS
     imag
    0.87
     souls
    0.83
    htaking
    0.78
     glimps
    0.78
     fleeting
    0.78
     glimpse
    0.75
     butterflies
    0.73
    phrase
    0.71
     hearts
    0.71
     prey
    0.70
    Act Density 0.062%

    No Known Activations