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

    Neuronpedia

    INDEX
    Explanations

    actions related to logging into accounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to logging into accounts or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gelatin
    -0.83
     coating
    -0.76
     tuber
    -0.68
     taste
    -0.67
     almond
    -0.66
    使
    -0.65
     hurd
    -0.65
     frost
    -0.65
     McMaster
    -0.63
     lethal
    -0.63
    POSITIVE LOGITS
     Username
    0.81
    ancy
    0.77
    ancies
    0.73
    priv
    0.72
    ername
    0.71
    ministic
    0.70
    activity
    0.70
    fol
    0.69
    efficients
    0.68
    country
    0.68
    Act Density 0.074%

    No Known Activations