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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms with a specific symbol inserted at the center

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unique symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$#$
    -0.70
    ysis
    -0.69
     dressing
    -0.69
    uers
    -0.67
    oller
    -0.67
    ŃĶ
    -0.66
     watered
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
    ijn
    -0.65
    zzy
    -0.64
    POSITIVE LOGITS
    style
    0.90
    ––
    0.90
    cases
    0.90
    backed
    0.84
    micro
    0.84
    based
    0.83
    time
    0.82
    issues
    0.82
    mediated
    0.82
    coll
    0.81
    Act Density 0.020%

    No Known Activations