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

    Neuronpedia

    INDEX
    Explanations

    actions of pulling or drawing attention in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.16
    838
    -0.15
    eme
    -0.14
    essed
    -0.14
    otel
    -0.14
    dos
    -0.13
    gain
    -0.13
    ÑĢÑĮ
    -0.13
    774
    -0.13
    vore
    -0.13
    POSITIVE LOGITS
     apart
    0.26
     strings
    0.26
    pull
    0.25
    ulate
    0.25
     rank
    0.24
     Plug
    0.23
     Apart
    0.23
     plug
    0.23
    ulan
    0.23
    .Pull
    0.22
    Act Density 0.024%

    No Known Activations