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

    Neuronpedia

    INDEX
    Explanations

    words related to collections or compiling things together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passage
    -0.77
    IELD
    -0.76
     Presence
    -0.69
    eanor
    -0.68
     Redemption
    -0.65
     Annotations
    -0.64
    hyde
    -0.64
    EED
    -0.63
    phasis
    -0.62
    izu
    -0.62
    POSITIVE LOGITS
    atorial
    0.87
    kered
    0.85
    ties
    0.85
    uded
    0.83
    enced
    0.82
    atable
    0.82
    uting
    0.81
    ted
    0.80
    ters
    0.79
    umin
    0.79
    Act Density 0.020%

    No Known Activations