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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal codes or similar technical data

    oai_token-act-pair · gpt-3.5-turbo

    sequences related to programming or data encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    busters
    -0.78
    nell
    -0.76
    sonian
    -0.74
    bank
    -0.73
    inals
    -0.71
    tin
    -0.70
    walk
    -0.67
    lie
    -0.66
    buster
    -0.65
    banks
    -0.64
    POSITIVE LOGITS
    xc
    1.31
    xd
    1.12
    xe
    1.10
    xf
    1.01
    xb
    1.01
    aminer
    0.94
    actly
    0.93
    âĶĢâĶĢâĶĢâĶĢ
    0.91
    elta
    0.85
    opard
    0.83
    Act Density 0.016%

    No Known Activations