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

    Neuronpedia

    INDEX
    Explanations

    prepositions or conjunctions indicating a relationship between different elements in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to invitations or social requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":-
    -0.73
    .",
    -0.71
    .:
    -0.69
    ses
    -0.66
     (?,
    -0.63
    ();
    -0.62
    usercontent
    -0.60
    ciplinary
    -0.59
    .;
    -0.59
    shed
    -0.59
    POSITIVE LOGITS
    arently
    0.86
    ardless
    0.85
     incidentally
    0.83
    etheless
    0.76
     spoiler
    0.76
    selves
    0.75
    !)
    0.75
    theless
    0.75
    ?)
    0.74
    lihood
    0.73
    Act Density 0.402%

    No Known Activations