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

    Neuronpedia

    INDEX
    Explanations

    words related to mechanical or technical features

    oai_token-act-pair · gpt-3.5-turbo

    words indicating measurements and structures in physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.64
    ONSORED
    -0.64
    HAEL
    -0.61
     Appropriations
    -0.60
    REDACTED
    -0.60
     Diary
    -0.55
    çĶ°
    -0.55
     ABE
    -0.54
    ,,,,
    -0.54
    aughed
    -0.53
    POSITIVE LOGITS
    otropic
    0.73
    ax
    0.71
    upp
    0.70
    otation
    0.66
    opl
    0.66
    acet
    0.66
    rit
    0.65
    act
    0.65
    umb
    0.65
    access
    0.64
    Act Density 0.734%

    No Known Activations