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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "in" and phrases that indicate presence or existence within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alem
    -0.15
    éģ
    -0.15
    291
    -0.15
     behalf
    -0.15
     sensitive
    -0.14
     tw
    -0.14
    callbacks
    -0.13
    leck
    -0.13
     sight
    -0.13
    yg
    -0.13
    POSITIVE LOGITS
     action
    0.53
    -action
    0.40
    action
    0.37
     ACTION
    0.35
    Action
    0.34
     Action
    0.33
    _action
    0.31
    .action
    0.30
     acción
    0.30
    ACTION
    0.29
    Act Density 0.044%

    No Known Activations