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

    Neuronpedia

    INDEX
    Explanations

    boolean expressions related to programming

    oai_token-act-pair · gpt-3.5-turbo

    boolean values and related programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agna
    -0.72
    hens
    -0.70
     resemblance
    -0.69
     reconc
    -0.68
    mast
    -0.66
     resemb
    -0.65
     Ging
    -0.61
    egal
    -0.59
    imil
    -0.58
    acus
    -0.56
    POSITIVE LOGITS
     }
    0.93
     &&
    0.93
     ||
    0.92
    ptr
    0.89
    },{"
    0.84
     },
    0.84
    false
    0.81
    }
    0.77
     guiActive
    0.77
     }}
    0.77
    Act Density 0.074%

    No Known Activations