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

    Neuronpedia

    INDEX
    Explanations

    personal reflections and expressions of emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    references to specific subjects denoted by "this" or "these"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¹ãĥĪ
    -0.99
    Īè
    -0.86
    Ĭ±
    -0.83
    ãĤ¶
    -0.78
    ãĥĭ
    -0.75
    ARS
    -0.73
    Ľ
    -0.72
    ·
    -0.72
    ivas
    -0.71
    ©¶æ¥µ
    -0.70
    POSITIVE LOGITS
     guy
    0.95
     kind
    0.84
     morning
    0.80
     sort
    0.79
     week
    0.77
     sucker
    0.76
     stuff
    0.76
     country
    0.74
     secrecy
    0.71
     wonderful
    0.71
    Act Density 0.226%

    No Known Activations