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

    Neuronpedia

    INDEX
    Explanations

    expressions related to horizontal orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UpInside
    -0.64
     ['$
    -0.62
    icio
    -0.59
     كومونز
    -0.55
     needle
    -0.55
    Abstra
    -0.55
    ecap
    -0.54
    imbawa
    -0.51
    ctose
    -0.51
    limat
    -0.51
    POSITIVE LOGITS
     Atlantic
    0.76
     atlantic
    0.68
    Atlantic
    0.68
     بيها
    0.66
     ATLANTIC
    0.66
     horizontally
    0.65
     Authentic
    0.64
    brake
    0.64
     brakes
    0.63
    horizontal
    0.63
    Act Density 0.037%

    No Known Activations