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

    Neuronpedia

    INDEX
    Explanations

    expressions describing a particular manner or approach of doing things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a manner or method of doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.72
    rament
    -0.72
    incinn
    -0.71
    encer
    -0.70
     Bei
    -0.69
    inus
    -0.67
    avorite
    -0.66
    ¥ŀ
    -0.65
    ishable
    -0.65
    anmar
    -0.64
    POSITIVE LOGITS
    abl
    0.76
    finding
    0.75
    forward
    0.75
    ward
    0.73
    fare
    0.70
     somew
    0.70
     resembles
    0.68
    WARD
    0.67
    hered
    0.67
     resembling
    0.66
    Act Density 0.031%

    No Known Activations