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

    Neuronpedia

    INDEX
    Explanations

    underscores and special characters associated with code or technical configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.71
    alist
    -0.69
     theoret
    -0.67
    EVA
    -0.66
    ONSORED
    -0.65
    Cub
    -0.65
     ANGEL
    -0.65
    sonian
    -0.65
    opian
    -0.64
    oths
    -0.63
    POSITIVE LOGITS
    7601
    0.88
    Downloadha
    0.87
     Affect
    0.79
     uninstall
    0.72
     disabling
    0.69
    583
    0.66
     persist
    0.65
    amacare
    0.64
     plag
    0.64
    364
    0.63
    Act Density 0.098%

    No Known Activations