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

    Neuronpedia

    INDEX
    Explanations

    The neuron looks for phrases indicating a recurring action or event

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "once again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Runner
    -0.65
    osit
    -0.63
     Treaty
    -0.63
    ĺħ
    -0.62
    otti
    -0.61
    OTS
    -0.59
    zie
    -0.59
    ohm
    -0.58
    rament
    -0.58
    adena
    -0.58
    POSITIVE LOGITS
    forth
    0.91
    nir
    0.81
    nces
    0.73
    brates
    0.72
    RGB
    0.71
     oblig
    0.71
    theless
    0.70
    brate
    0.69
     conclud
    0.68
    atility
    0.65
    Act Density 0.022%

    No Known Activations