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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences with complex language or formal tone

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.77
     shack
    -0.75
     dumping
    -0.73
     decomp
    -0.71
     publicity
    -0.68
     assistance
    -0.67
     convenience
    -0.67
     gib
    -0.67
     dividing
    -0.65
     collecting
    -0.64
    POSITIVE LOGITS
    £
    0.96
    º
    0.93
    acca
    0.88
    ¹
    0.84
    ĸļ
    0.81
    thus
    0.78
    į
    0.78
    ¡
    0.77
    must
    0.76
    alone
    0.76
    Act Density 0.289%

    No Known Activations