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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "directed"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directed"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.71
    iders
    -0.70
    tex
    -0.68
     Mell
    -0.66
    inventoryQuantity
    -0.63
    iddler
    -0.61
     Sloven
    -0.61
    pton
    -0.61
    ollen
    -0.60
     Frag
    -0.59
    POSITIVE LOGITS
     toward
    0.94
    ovie
    0.93
    irection
    0.91
    irect
    0.91
     directed
    0.87
     towards
    0.86
    nance
    0.84
    htaking
    0.82
    RECT
    0.80
     directing
    0.77
    Act Density 0.022%

    No Known Activations