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

    Neuronpedia

    INDEX
    Explanations

    references to the word "bat" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoff
    -0.21
    orgh
    -0.16
    parator
    -0.15
    oran
    -0.15
    adoo
    -0.15
    .nih
    -0.15
     Vit
    -0.15
    nees
    -0.15
    Operators
    -0.15
    idge
    -0.15
    POSITIVE LOGITS
    htub
    0.26
     Bat
    0.23
    Bat
    0.21
    wing
    0.21
    eman
    0.20
    tement
    0.20
    avia
    0.20
     bat
    0.19
    lle
    0.19
    ista
    0.18
    Act Density 0.010%

    No Known Activations