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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "into" and its variations, indicating a focus on movement or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âgées
    -0.81
    rubin
    -0.73
    GRAPH
    -0.73
     Weh
    -0.73
    Busch
    -0.73
     africains
    -0.72
    veil
    -0.71
     marins
    -0.70
     conservé
    -0.70
     secas
    -0.70
    POSITIVE LOGITS
    Into
    1.56
     INTO
    1.55
     Into
    1.53
     into
    1.42
    INTO
    1.31
    into
    1.10
     onto
    1.00
    soever
    0.88
    rungsseite
    0.84
    Jays
    0.83
    Act Density 0.110%

    No Known Activations